PhD Studentship: Developing continuity of care prediction models using Explainable AI for outcomes of care in multimorbid patients: the example of heart failure (HF) and chronic obstructive pulmonary disease (COPD)

Project description:

There is well-established evidence from primary care that continuity of care with a single healthcare professional, such as a GP, can lead to improved care and clinical outcomes. However, this key concept has diminished as multiple long-term condition pathways and multi-disciplinary teams have superseded the idea of a primary HCP responsible for coordinating care. There is a significant gap in the evidence on how these changes have impacted care and outcomes, and how different measures of continuity-of-care are incorporated in AI/ML predictive models of outcomes.

The aims of the studentship are to develop AI/ML predictive models of outcomes using new measures of continuity of care based on routinely collected clinical and care data, for the population with heart failure and chronic obstructive pulmonary disease.

There will be three stages to the studentship: (i) Systematic review of the literature on continuity of care measures and application in AI/ML prediction models using routinely collected care data; (ii) Development of AI/ML predictive models using the anonymised Clinical Practice Research Datalink (CPRD) database for adults with multiple conditions of heart failure and chronic obstructive pulmonary disease, which require high levels of care; (iii) Performance testing of these AI/ML predictive models using specified clinical and care outcomes for HF and COPD.

This PhD studentship is a data science project in the healthcare domain and as such will provide experience of handling ‘big data’, developing AI/ML methods and translation of methods into practice, working with PPI. Development will take place in an inter-disciplinary team for a dynamic career as a healthcare data scientist

Advert information